# April 1996, Volume 5, Number 1

**D. Levicky, M. Drutarovsky, P. Galajda, D. Kocur, S. Marchevsky**
[full-text]

Adaptive Goertzel's Algorithm for DFT Computation with Higher Accuracy

In this paper the adaptive Goertzel's algorithm applied for required DFT coefficient computation in the harmonic analyser is described. This algorithm utilizes effective combination of the synchronous DFT and window method. The experiments with the adaptive Goerzel's algorithm given in this paper have shown that in the case of a harmonic analysis of periodical triangular wave it can provide the accuracy of the harmonic computation better than 0.01%.

**J. Nahlik, L. Hudec**
[full-text]

To the Possibility of Calculation of Phase Synchronism Active Range in Two-Modes Laser

The contribution intends to promote further application possibilities of Donocik's method for stability investigation of dynamical systems and presents a nontrivial application - the attempt to calculate a phase synchronism active range of two oscillating modes in a laser by attraction regions of stationary states of a nonlinear system testing. The emphasis is laid upon a final discussion

**P. Nevriva**
[full-text]

Data Description of a System

In this paper, a brief discussion on description of process by memorized data is given. The insight into the problem can offer modified views on optimal control, on data compression at communication systems with respect to information content of message, etc. The idea of process description by memorized data with different information content will be presented here on the classical case study of optimal control: the data based control algorithm (data algorithm, DA) gathers data from the controlled process and derives control signal (control) from data accumulated in the data base. The implementation of the DA on the ideal computer which is not limited by its speed or capacity of memory is expected for simplicity. Accuracy of the data algorithm is then given by a-priori knowledge of the task and by information exchange between the controlled process and the computer.

**J. Tuckova, P. Bores**
[full-text]

Influence of the Number of the Features with the Neural Network Function

This contribution is devoted to the evaluation of probability of success for classification and recognition techniques. It also depends on a proper selection of input elements-features and their number. Error probability is proportional indirectly on a quantity and quality of information provided to a classifier. It can be affected either by a learning algorithm itself and classification or by an element number on classification correctuers has been verified for Kohonen's map designed for a recognition of Czech digits.

**D. Kocur, M. Drutarovsky, S. Marchevsky**
[full-text]

A New Glass of Nonlinear Filters: Microstatistic Volterra Filters

In this paper a new subset of the time-invariant microstatistic filters so-called microstatistic Volterra filters are proposed. This class of nonlinear filters is based on the idea of the conventional microstatistic filter generalization by substituting Wiener filters applied in the conventional microstatistic filter structure by Volterra filters. The advantage of the microstatistic Volterra filters in comparison with the Wiener filters, Volterra filters and conventional microstatistic filters is the fact that in the case of non-Gaussian signal processing the microstatistic Volterra filters can outperform Wiener filters, Volterra filters or conventional microstatistic filters. The validity of this basic property of the microstatistic Volterra filters is verified by a number of computer experiments. The disadvantage of the microstatistic Volterra filters is their relatively high computational complexity.

**J. Nouza**
[full-text]

A Two-Level Classification Scheme for CDHMM-Based Discrete-Utterance Recognition

In the paper a method of speeding up the response of a CDHMM based speech recognition system is introduced. The method, applicable for the recognition of discrete utterances, uses a two-level classification scheme. It consists in a fast match done with simplified models, followed by a final accurate match with a limited number of selected standard models. In this way the recognition time can be reduced by great deal without any significant loss of recognition accuracy. The method has been successfully applied in the design of real-time speech recognition systems operating with small and middle-size vocabularies.

**L. Bazant**
[full-text]

The Computation of Forward Scattered Functions for Pruppacher - Pitter Raindrop Forms at 37 GHz

The amplitude scattered functions were computed for Pruppacher - Pitter raindrop forms at 37 GHz by using the Multiple MultiPole numerical method. Before doing that the measurement of the complex permittivity of rain water had been performed at the same frequency and rain water complex permittivity values had been determined.

**H. El Hamchary**
[full-text]

Optimisation of Microstrip Antenna

When choosing the most appropriate microstrip antenna configuration for particular applications, the kind of excitation of the radiating element is an essential factor that requires careful considerations. For controlling the distribution of energy of the linear or planar array of elements and for coupling energy to the individual elements, a wide variety of feed mechanisms are available. In this paper, the coaxial antenna feeding is assumed and the best (optimised) feeding is found. Then, antenna characteristics such as radiation pattern, return loss, input impedance, and VSWR are obtained.